© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 125715
    Prev
    Next
    INDEX
    Explanations

    mentions of popular recording artists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĥÑĢа
    -0.08
    ctor
    -0.07
    eko
    -0.07
    apel
    -0.07
    anke
    -0.07
    arin
    -0.07
    ogui
    -0.07
    á»ijt
    -0.07
    antino
    -0.07
    egen
    -0.07
    POSITIVE LOGITS
     ones
    0.06
    Multiplicity
    0.06
    474
    0.06
    <<(
    0.05
    cul
    0.05
    PlainText
    0.05
     Schwartz
    0.05
    lat
    0.05
     LENG
    0.05
    ulf
    0.05
    Activations Density 0.029%

    No Known Activations